© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208824
    Prev
    Next
    INDEX
    Explanations

    object preposition

    np_acts-logits-general · gemini-2.5-flash-lite

    input to services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ;
    0.54
     ؛
    0.48
    respuesta
    0.47
    another
    0.46
    pora
    0.46
    另一个
    0.45
     ="
    0.45
    startGame
    0.45
     மற்றொரு
    0.45
    larını
    0.44
    POSITIVE LOGITS
     begge
    0.49
    ス
    0.47
     Asoci
    0.46
    年前
    0.45
     Doug
    0.45
     rmg
    0.45
     wissen
    0.45
     Vai
    0.45
     rea
    0.44
     Pret
    0.44
    Activations Density 0.001%

    No Known Activations